{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2018:YI2S4METVIU4TKXXWG4ZXJHTNE","short_pith_number":"pith:YI2S4MET","schema_version":"1.0","canonical_sha256":"c2352e3093aa29c9aaf7b1b99ba4f3690792a7a7e39e9c4b44b38b93add0150b","source":{"kind":"arxiv","id":"1805.10965","version":2},"attestation_state":"computed","paper":{"title":"Lipschitz regularity of deep neural networks: analysis and efficient estimation","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.LG"],"primary_cat":"stat.ML","authors_text":"Aladin Virmaux, Kevin Scaman","submitted_at":"2018-05-28T15:08:15Z","abstract_excerpt":"Deep neural networks are notorious for being sensitive to small well-chosen perturbations, and estimating the regularity of such architectures is of utmost importance for safe and robust practical applications. In this paper, we investigate one of the key characteristics to assess the regularity of such methods: the Lipschitz constant of deep learning architectures. First, we show that, even for two layer neural networks, the exact computation of this quantity is NP-hard and state-of-art methods may significantly overestimate it. Then, we both extend and improve previous estimation methods by "},"verification_status":{"content_addressed":true,"pith_receipt":true,"author_attested":false,"weak_author_claims":0,"strong_author_claims":0,"externally_anchored":false,"storage_verified":false,"citation_signatures":0,"replication_records":0,"graph_snapshot":true,"references_resolved":false,"formal_links_present":false},"canonical_record":{"source":{"id":"1805.10965","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"stat.ML","submitted_at":"2018-05-28T15:08:15Z","cross_cats_sorted":["cs.LG"],"title_canon_sha256":"ac83fd4dbadc11aba2a847602b86e1501aac5a342359e55f1ed68a13d73099ce","abstract_canon_sha256":"64b4ec9e8f7fa3a6a348703fefdc615d17cbbd7aefc6bf2e65b32c308833a37e"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T00:14:42.936507Z","signature_b64":"F+TQENurWWopZBX9lLKRwi3Qde4Z27QPv9iLQOEen+mbvgtir6r9Cz74t2zki3A06soxI9I3XOFKNRv9B/TfAA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"c2352e3093aa29c9aaf7b1b99ba4f3690792a7a7e39e9c4b44b38b93add0150b","last_reissued_at":"2026-07-05T00:14:42.936069Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T00:14:42.936069Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Lipschitz regularity of deep neural networks: analysis and efficient estimation","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.LG"],"primary_cat":"stat.ML","authors_text":"Aladin Virmaux, Kevin Scaman","submitted_at":"2018-05-28T15:08:15Z","abstract_excerpt":"Deep neural networks are notorious for being sensitive to small well-chosen perturbations, and estimating the regularity of such architectures is of utmost importance for safe and robust practical applications. In this paper, we investigate one of the key characteristics to assess the regularity of such methods: the Lipschitz constant of deep learning architectures. First, we show that, even for two layer neural networks, the exact computation of this quantity is NP-hard and state-of-art methods may significantly overestimate it. Then, we both extend and improve previous estimation methods by "},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1805.10965","kind":"arxiv","version":2},"verdict":{"id":null,"model_set":{},"created_at":null,"strongest_claim":"","one_line_summary":"","pipeline_version":null,"weakest_assumption":"","pith_extraction_headline":""},"integrity":{"clean":true,"summary":{"advisory":0,"critical":0,"by_detector":{},"informational":0},"endpoint":"/pith/1805.10965/integrity.json","findings":[],"available":true,"detectors_run":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938"},"references":{"count":0,"sample":[],"resolved_work":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57","internal_anchors":0},"formal_canon":{"evidence_count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"author_claims":{"count":0,"strong_count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"builder_version":"pith-number-builder-2026-05-17-v1"},"aliases":[{"alias_kind":"arxiv","alias_value":"1805.10965","created_at":"2026-07-05T00:14:42.936130+00:00"},{"alias_kind":"arxiv_version","alias_value":"1805.10965v2","created_at":"2026-07-05T00:14:42.936130+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1805.10965","created_at":"2026-07-05T00:14:42.936130+00:00"},{"alias_kind":"pith_short_12","alias_value":"YI2S4METVIU4","created_at":"2026-07-05T00:14:42.936130+00:00"},{"alias_kind":"pith_short_16","alias_value":"YI2S4METVIU4TKXX","created_at":"2026-07-05T00:14:42.936130+00:00"},{"alias_kind":"pith_short_8","alias_value":"YI2S4MET","created_at":"2026-07-05T00:14:42.936130+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":0,"internal_anchor_count":0,"sample":[]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/YI2S4METVIU4TKXXWG4ZXJHTNE","json":"https://pith.science/pith/YI2S4METVIU4TKXXWG4ZXJHTNE.json","graph_json":"https://pith.science/api/pith-number/YI2S4METVIU4TKXXWG4ZXJHTNE/graph.json","events_json":"https://pith.science/api/pith-number/YI2S4METVIU4TKXXWG4ZXJHTNE/events.json","paper":"https://pith.science/paper/YI2S4MET"},"agent_actions":{"view_html":"https://pith.science/pith/YI2S4METVIU4TKXXWG4ZXJHTNE","download_json":"https://pith.science/pith/YI2S4METVIU4TKXXWG4ZXJHTNE.json","view_paper":"https://pith.science/paper/YI2S4MET","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=1805.10965&json=true","fetch_graph":"https://pith.science/api/pith-number/YI2S4METVIU4TKXXWG4ZXJHTNE/graph.json","fetch_events":"https://pith.science/api/pith-number/YI2S4METVIU4TKXXWG4ZXJHTNE/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/YI2S4METVIU4TKXXWG4ZXJHTNE/action/timestamp_anchor","attest_storage":"https://pith.science/pith/YI2S4METVIU4TKXXWG4ZXJHTNE/action/storage_attestation","attest_author":"https://pith.science/pith/YI2S4METVIU4TKXXWG4ZXJHTNE/action/author_attestation","sign_citation":"https://pith.science/pith/YI2S4METVIU4TKXXWG4ZXJHTNE/action/citation_signature","submit_replication":"https://pith.science/pith/YI2S4METVIU4TKXXWG4ZXJHTNE/action/replication_record"}},"created_at":"2026-07-05T00:14:42.936130+00:00","updated_at":"2026-07-05T00:14:42.936130+00:00"}